Self-Supervised Physics-Based Deep Learning MRI Reconstruction Without Fully-Sampled Data

TL;DR

This paper introduces a self-supervised deep learning method for MRI reconstruction that does not require fully-sampled data, enabling high-quality image recovery in scenarios where such data is difficult to obtain.

Contribution

The work presents a novel self-supervised training strategy for physics-based MRI reconstruction that eliminates the need for fully-sampled datasets during training.

Findings

Self-supervised method achieves comparable results to supervised approaches.

Effective reconstruction without fully-sampled data in challenging scenarios.

Potential application to other inverse problems without complete data.

Abstract

Deep learning (DL) has emerged as a tool for improving accelerated MRI reconstruction. A common strategy among DL methods is the physics-based approach, where a regularized iterative algorithm alternating between data consistency and a regularizer is unrolled for a finite number of iterations. This unrolled network is then trained end-to-end in a supervised manner, using fully-sampled data as ground truth for the network output. However, in a number of scenarios, it is difficult to obtain fully-sampled datasets, due to physiological constraints such as organ motion or physical constraints such as signal decay. In this work, we tackle this issue and propose a self-supervised learning strategy that enables physics-based DL reconstruction without fully-sampled data. Our approach is to divide the acquired sub-sampled points for each scan into training and validation subsets. During training, data consistency is enforced over the training subset, while the validation subset is used to define the loss function. Results show that the proposed self-supervised learning method successfully reconstructs images without fully-sampled data, performing similarly to the supervised approach that is trained with fully-sampled references. This has implications for physics-based inverse problem approaches for other settings, where fully-sampled data is not available or possible to acquire.